Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20344
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Brown."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Brown."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.81
    udeau
    -0.81
    olated
    -0.78
    isSpecialOrderable
    -0.78
    adena
    -0.75
    Lex
    -0.75
    yrim
    -0.74
    DCS
    -0.74
    ITAL
    -0.73
    peria
    -0.72
    POSITIVE LOGITS
    lee
    0.97
    ing
    0.89
    coat
    0.87
    low
    0.82
    ells
    0.82
    ell
    0.80
    horn
    0.80
    beard
    0.79
    stein
    0.78
    erton
    0.77
    Activations Density 0.011%

    No Known Activations